A News Archive That Doesn't Work for New Coverage

A news agency's archive of past publications grows for years but is barely used when working on new material: a journalist writes about a developing story without knowing the agency already covered it three years ago — because finding that is only possible through an exact keyword match in the headline.

Digercules goes through the publication archive and builds a content index from it — topics, people, events — so a new publication can be automatically linked to relevant past material, even when the wording doesn't match.

How it works

Processing runs either entirely on the client's own hardware, or — if that hardware isn't powerful enough — is delegated to a specific external machine over a closed peer-to-peer channel (not a public cloud): the compute is physically located in the Caucasus and Eastern Europe, the client is always told explicitly which machine and which jurisdiction is doing the processing, and only text/structured results come back — never the source files.

Objections

"We have internal CMS search" — CMS search usually looks for exact words in the text or headline; Digercules finds the connection by meaning — topic, person, event — even when the wording has changed over the years.

"The staff already knows the agency's archive" — that works for a small newsroom with a long-tenured team; it stops working once a generation of journalists turns over, or the archive grows across decades of publications.

First contact

A pilot on the publication archive for one topic or region over a few years — a demonstration of automatic cross-linking with new material. The decision on access to the publication archive sits with the editor-in-chief, not a line journalist.